We present a method for unsupervised discovery of abnormal occurrences of activities in multi-dimensional time series data. Unsupervised activity discovery approaches differ from ...
Abstracts "Mixtures at the Interface" David Scott, Rice University Mixture modeling provides an effective framework for complex, high-dimensional data. The potential of m...
The ParaStation communication fabric provides a high-speed communicationnetwork with user-levelaccess to enable e cientparallel computing on workstation clusters. The architecture...
Thomas M. Warschko, Joachim M. Blum, Walter F. Tic...
We derive a family of kernels on dynamical systems by applying the Binet-Cauchy theorem to trajectories of states. Our derivation provides a unifying framework for all kernels on d...
S. V. N. Vishwanathan, Alexander J. Smola, Ren&eac...
Abstract. More and more free multi-party video conferencing applications are readily available over the Internet and both Server-to-Client (S/C) or Peer-to-Peer (P2P) technologies ...
Yue Lu, Yong Zhao, Fernando A. Kuipers, Piet Van M...